Abstract: In a speech recognition session, a method of speech processing utilizing a plurality of grammars can include a series of steps. The method can include spawning a separate thread of execution corresponding to each one of a plurality grammars and allocating a post-processing recognition task to each separate thread of execution. Each post-processing recognition task can produce a possible recognition result using the corresponding grammar. A possible recognition result produced by one of the post-processing recognition tasks can be identified.

Abstract: A method of generating a grammar for recognizing headings in a speech recognition system can include identifying, within a data store, at least one heading selection associated with a content item. At least a first word from the identified heading selections can be extracted and a heading grammar automatically can be generated by including each extracted word of the identified heading selections within the heading grammar.

Abstract: A method for guiding text-to-speech output timing with speech recognition markers can include the following steps. First, tokens can be retrieved in a TTS system. The tokens can include words, phrase markers, punctuation marks and meta-tags. Second, phrase markers can be identified among the retrieved tokens. Third, words can be identified among the retrieved tokens. Fourth, the TTS system can TTS play back the identified words. Finally, during the TTS playback of the words, the TTS system can pause in response to the identification of the phrase markers.

Abstract: A voice spelling method. A voice spelling method can include the steps of: in an audio-only interface, receiving a plurality of audio signals representative of spoken characters, the plurality of spoken characters specifying a string; and, through the audio-only interface, providing audible feedback in between each received spoken character. Additionally, the method can include the steps of: through the audio-only interface, audibly playing back each spoken character; accepting a voice selection of one of the played back characters, the selection denoting a disputed character; identifying a replacement character; and, replacing the disputed character with the identified replacement character in the specified string.

Abstract: A method for performing speech recognition can include determining a recognition result for received user speech. The recognition result can include recognized text and a corresponding confidence score. The confidence score of the recognition result can correspond to a predetermined minimum threshold. If the confidence score does not exceed the predetermined minimum threshold, the user can be presented with at least one empirically determined alternate word candidate corresponding to the recognition result.

Abstract: A speech input method editor can include a speech toolbar (102) having at least a microphone state/toggle button (104). The speech input method editor can also include a selectable dictation window area (108) used as a temporary dictation target until dictation text is transferred to a target application and a selectable correction window area (112) having at least one among an alternate list (120) for correcting dictated words, an alphabet (114), a spacebar (116), a spell mode reminder (118), or a virtual keyboard (122). The speech input method editor can remain active while using the selectable correction window and while transferring dictation text to the target application. The speech input method editor can further include an alternate input method editor window (112b) used to allow non-speech editing into at least one among the dictation window or to the target application while using the speech input method editor.

Abstract: A system and method for automatically providing quality assurance for user enrollment in a recognition system. Advantageously, the quality a new enrollment (i.e., a newly trained user-dependent prototype) is assessed before the new enrollment is accepted in place of a current enrollment. This quality check is performed by decoding stored user test data using the new enrollment, comparing the decoding results of the new enrollment to the known script used to generate the test data to obtain an accuracy score for the new enrollment, and then comparing the accuracy score for the new enrollment with an accuracy score of a previous qualified enrollment (or, in the case where there is no previous, qualified enrollment, to the accuracy of the speaker independent model). If the decoding results of the new enrollment are acceptable, the new enrollment will be used for recognition; otherwise it will be rejected and discarded.

Abstract: A method for discriminating between an instance of a voice command and an instance of speech dictation can include identifying a focus point in a user interface; defining a surrounding region about the focus point; identifying user interface objects in the surrounding region; further identifying among the identified user interface objects those user interface objects which are configured to accept speech dictated text and those user interface objects which are not configured to accept speech dictated text; computing a probability based upon those user interface objects which have been further identified as being configured to accept speech dictated text and those user interface objects which have been further identified as not being configured to accept speech dictated text; receiving speech input; and, biasing a determination of whether the speech input is a voice command or speech dictation based upon the computed probability.

Abstract: In a speech recognition system, a method of providing a concise form of a natural command can include receiving a user specified command and identifying all functionally equivalent natural command forms of the user specified command from a natural command grammar. The length of each functionally equivalent natural command form can be determined. The method also can include presenting a selected one of the functionally equivalent natural command forms having the shortest length to the user.

Abstract: A method for discriminating between an instance of a voice command and an instance of speech dictation can include identifying a focus point in a user interface; defining a surrounding region about the focus point; identifying user interface objects in the surrounding region; further identifying among the identified user interface objects those user interface objects which are configured to accept speech dictated text and those user interface objects which are not configured to accept speech dictated text; computing a probability based upon those user interface objects which have been further identified as being configured to accept speech dictated text and those user interface objects which have been further identified as not being configured to accept speech dictated text; receiving speech input; and, biasing a determination of whether the speech input is a voice command or speech dictation based upon the computed probability.

Abstract: An assembly for rapidly filing bathtubs, whirlpools, spas, washing machine drums and the like includes a basin, water storage tank(s) (such as hot and cold water storage tanks), and a system for controlling the filling of the basin from the tank(s). When it is desired to supply water to the basin, this is expedited by placing the tank(s) above the basin, using connecting piping with extra large area, using a pressure pump, and/or providing extra large delivery ports. The tank(s) are dedicated to the assembly, and preferably are closely adjacent thereto. Controls are provided to avoid excess weight gathering adjacent the basin.

Abstract: The invention concerns a method and a system for transcribing a voice mail message. The method of the invention involves a plurality of steps including, first providing a computer voice mail message stored in an audio file to a computer speech recognition system and, second, submitting the computer voice mail message to a speaker identification process in the speech recognition system. Notably, the speaker identification process can identify an enrolled speaker as a source of the computer voice mail message. Finally, responsive to the identification of the enrolled speaker, the computer voice mail message can be submitted to a speech conversion process in the speech recognition system. The speech conversion process can perform speech-to-text conversion of the computer voice mail message using speaker enrollment data corresponding to the identified enrolled speaker. Furthermore, the speech-to-text conversion can produce a transcription of the computer voice mail message.

Abstract: A method of selecting a language model for decoding received user spoken utterances in a speech recognition system can include a series of steps. The steps can include computing confidence scores for identified closed-class words and computing a running average of the confidence scores for a predetermined number of decoded closed-class words. Additionally, based upon the running average, telegraphic decoding can be selectively enabled.

Abstract: A method of proofreading and correcting dictated text contained in an electronic document can include selecting proofreading criteria for identifying textual errors contained in the electronic document; playing back each word contained in the electronic document; and, marking as a textual error each played back word in nonconformity with at least one of the proofreading criteria.

Abstract: A method for concurrent presentation of multiple audio information sources. In the method, audio information from at least two audio information sources is concurrently presented, and a user speech selection of one of the audio information sources is accepted. At least one of the audio information sources can then be reconfigured. The reconfiguration audibly distinguishes the user selected audio information source from other audio information sources.

Abstract: A method and system uses a finite state command grammar coordinated with application scripting to recognize voice command structures for performing an event from an initial location to a new location. The method involves a series of steps, including: recognizing an enabling voice command specifying the event to be performed from the initial location; determining a functional expression for the enabling voice command defined by one or more actions and objects; storing the action and object in a memory location; receiving input specifying the new location; recognizing an activating voice command for performing the event up to the new location; retrieving the stored action and object from the memory location; and performing the event from the initial location to the new location according to the retrieved action and object. Preferably, the enabling-activating command is phrased as “from here . . . to here”.

Abstract: A method and a machine-readable storage for operation of a combobox in a graphical user interface (GUI). Conditions are defined which indicate an accessibility of items for presentation in a listbox associated with the combobox and particular ones of the conditions are associated with the combobox. The associated conditions are consulted to dynamically determine the accessibility of the items for the listbox during operation of a program. Further, if items are inaccessible for the listbox, the inaccessibility of the listbox is automatically visually indicated in accordance with the consulting step.

Abstract: A transcription system (100) includes a computer (102), a monitor (104), and a microphone (110). Via the microphone, a user of the system provides input speech that is received and transcribed (204) by the system. The system monitors (205) the accuracy of the transcribed speech during transcription. The system also determines (210) whether the accuracy of the transcribed speech is sufficient and, if not, automatically activates (214) a speech recognition improvement tool and alerts (212) the user that the tool has been activated.

Abstract: A method for voice data entry availability in a voice response system can include receiving speech input specifying data in an audio user interface to a data information system for processing data in a data store. The speech input can be received through an audio user interface to the data information system. Subsequently, speech-to-text conversion of the speech input can be performed using a speech recognition engine with reference to a corresponding speech grammar. In particular, the speech grammar can contain a data set of words relating to the data information system. Notably, the data store can contain a subset of the data set, the subset having words which can be processed by the data information system, the subset not having words which cannot be processed by the data information system. If the specified data is included in the speech grammar and if the specified data is in the data store, the speech data in the speech query can be processed.

Abstract: A method for adjusting a speech menu interface in a speech recognition system. The method can include a series of steps which can include identifying one or more menu items from a data structure in memory for presentation using the speech menu interface. The step of retrieving the one or more menu items from the data structure can be included. Also, the step of reading at least one attribute corresponding to the one or more menu items with menu item criteria can be included. Based on the comparing step, the method can include selecting a presentation style for presentation of the one or more menu items using the speech menu interface.